Probabilistic Machine-Learning Methods for Performance Prediction of Structure and Infrastructures through Natural Gradient Boosting
Publication: Journal of Structural Engineering
Volume 148, Issue 8
Abstract
The capabilities of data-driven models based on machine learning (ML) algorithms in offering accurate predictions of structural responses efficiently have been demonstrated in numerous recent studies. However, efforts to date have relied on essentially deterministic approaches, and prediction confidence measures were either derived from verification data sets or completely ignored. This study examined the potential of a new algorithm—natural gradient boosting (NGBoost)—that directly produces probabilistic predictions. This type of output fits the reliability and performance analysis frameworks naturally, and also opens the pathways to utilization of self-learning algorithms and optimal design of experiments and field measurement campaigns in engineering applications. After introducing NGBoost’s fundamentals, two representative problems in structural engineering were investigated to examine NGBoost’s feasibility: (1) prediction of the strengths of squat shear walls, and (2) classification of the seismic damage levels in ordinary bridges. The results indicate that NGBoost attains mean prediction accuracy levels comparable to those of conventional ML algorithms while providing robust estimates of prediction uncertainties.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The authors greatly appreciate the financial support from National Natural Science Foundation of China (Nos. 52078119 and 52008027), the General Project Supported by Natural Science Basic Research Plan in Shaanxi Province of China (No. 2021JQ-269), and Fundamental Research Funds for the Central Universities, CHD (No. 300102211304). The first and third authors also acknowledge support by the China Scholarship Council and Southeast University’s Zhi-Shan Scholarship Program, respectively, which enabled them to spend time as visiting scholars at UCLA.
References
ACI (American Concrete Institute). 2014. Building code requirements for structural concrete. ACI 318-14. Farmington Hills, MI: ACI.
Alotaibi, E., O. Mostafa, N. Nassif, M. Omar, and M. G. Arab. 2021. “Prediction of punching shear capacity for fiber-reinforced concrete slabs using neuro-nomographs constructed by machine learning.” J. Struct. Eng. 147 (6): 04021075. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003041.
Amari, S.-I. 1998. “Natural gradient works efficiently in learning.” Neural Comput. 10 (2): 251–276. https://doi.org/10.1162/089976698300017746.
ASCE. 2005. Seismic design criteria for structures, systems, and components in nuclear facilities. ASCE 43-05. Reston, VA: ASCE.
Baker, J. W., T. Lin, S. K. Shahi, and N. Jayaram. 2011. New ground motion selection procedures and selected motions for the PEER transportation research program. Berkeley, CA: Pacific Earthquake Engineering Research Center, College of Engineering Univ. of California.
Boehmke, B., and B. Greenwell. 2018. Hands-on machine learning with R. London: Chapman and Hall/CRC Press.
Castaldo, P., and G. Amendola. 2021a. “Optimal DCFP bearing properties and seismic performance assessment in nondimensional form for isolated bridges.” Earthquake Eng. Struct. Dyn. 50 (9): 2442–2461. https://doi.org/10.1002/eqe.3454.
Castaldo, P., and G. Amendola. 2021b. “Optimal sliding friction coefficients for isolated viaducts and bridges: A comparison study.” Struct. Control Health Monit. 28 (12): e2838. https://doi.org/10.1002/stc.2838.
Castaldo, P., D. Gino, G. Bertagnoli, and G. Mancini. 2018. “Partial safety factor for resistance model uncertainties in 2D non-linear finite element analysis of reinforced concrete structures.” Eng. Struct. 176 (Dec): 746–762. https://doi.org/10.1016/j.engstruct.2018.09.041.
Castaldo, P., D. Gino, and G. Mancini. 2019. “Safety formats for non-linear finite element analysis of reinforced concrete structures: Discussion, comparison and proposals.” Eng. Struct. 193 (Aug): 136–153. https://doi.org/10.1016/j.engstruct.2019.05.029.
Chen, S.-Z., and D.-C. Feng. 2022. “Multifidelity approach for data-driven prediction models of structural behaviors with limited data.” Comput.-Aided Civ. Infrastruct. Eng. https://doi.org/10.1111/mice.12817.
Chen, S.-Z., D.-C. Feng, W.-S. Han, and G. Wu. 2021a. “Development of data-driven prediction model for CFRP-steel bond strength by implementing ensemble learning algorithms.” Constr. Build. Mater. 303 (Oct): 124470. https://doi.org/10.1016/j.conbuildmat.2021.124470.
Chen, S.-Z., D.-C. Feng, and Z. Sun. 2021b. “Reliability-based vehicle weight limit determination for urban bridge network subjected to stochastic traffic flow considering vehicle-bridge coupling.” Eng. Struct. 247 (Nov): 113166. https://doi.org/10.1016/j.engstruct.2021.113166.
Chen, S.-Z., S.-Y. Zhang, W.-S. Han, and G. Wu. 2021c. “Ensemble learning based approach for FRP-concrete bond strength prediction.” Constr. Build. Mater. 302 (Oct): 124230. https://doi.org/10.1016/j.conbuildmat.2021.124230.
Cui, W., T. Ma, L. Zhao, and Y. Ge. 2021. “Data-based windstorm type identification algorithm and extreme wind speed prediction.” J. Struct. Eng. 147 (5): 04021053. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002954.
Deierlein, G. G., and A. Zsarnóczay. 2021. State of the art in computational simulation for natural hazards engineering. NHERI SimCenter.
Der Kiureghian, A., and O. Ditlevsen. 2009. “Aleatory or epistemic? Does it matter?” Struct. Saf. 31 (2): 105–112. https://doi.org/10.1016/j.strusafe.2008.06.020.
Duan, T., A. Anand, D. Y. Ding, K. K. Thai, S. Basu, A. Ng, and A. Schuler. 2020. “NGBoost: Natural gradient boosting for probabilistic prediction.” In Proc., Int. Conf. on Machine Learning, 2690–2700. New York: Machine Learning Research Press.
Dukes, J., S. Mangalathu, J. E. Padgett, and R. DesRoches. 2018. “Development of a bridge-specific fragility methodology to improve the seismic resilience of bridges.” Earthquakes Struct. 15 (3): 253–261. https://doi.org10.12989/eas.2018.15.3.253.
Eddelbuettel, D. 2013. “A gentle introduction to gradient boosting.” In Seamless R and C++ integration with Rcpp.
Eliason, S. R. 1993. Maximum likelihood estimation: Logic and practice. Thousand Oaks, CA: SAGE.
El-Sefy, M., A. Yosri, W. El-Dakhakhni, S. Nagasaki, and L. Wiebe. 2021. “Artificial neural network for predicting nuclear power plant dynamic behaviors.” Nucl. Eng. Technol. 53 (10): 3275–3285. https://doi.org/10.1016/j.net.2021.05.003.
FEMA. 2018. Hazus–MH 2.1 technical manual. Washington, DC: FEMA.
Feng, D.-C., B. Cetiner, M. R. Azadi Kakavand, and E. Taciroglu. 2021a. “Data-driven approach to predict the plastic hinge length of reinforced concrete columns and its application.” J. Struct. Eng. 147 (2): 04020332. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002852.
Feng, D.-C., S.-Z. Chen, M. R. Azadi Kakavand, and E. Taciroglu. 2021b. “Probabilistic model based on Bayesian model averaging for predicting the plastic hinge lengths of reinforced concrete columns.” J. Eng. Mech. 147 (10): 04021066. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001976.
Feng, D.-C., Z.-T. Liu, X.-D. Wang, Y. Chen, J.-Q. Chang, D.-F. Wei, and Z.-M. Jiang. 2020a. “Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach.” Constr. Build. Mater. 230 (Jan): 117000. https://doi.org/10.1016/j.conbuildmat.2019.117000.
Feng, D.-C., Z.-T. Liu, X.-D. Wang, Z.-M. Jiang, and S.-X. Liang. 2020b. “Failure mode classification and bearing capacity prediction for reinforced concrete columns based on ensemble machine learning algorithm.” Adv. Eng. Inf. 45 (Aug): 101126. https://doi.org/10.1016/j.aei.2020.101126.
Feng, D.-C., W.-J. Wang, S. Mangalathu, G. Hu, and T. Wu. 2021c. “Implementing ensemble learning methods to predict the shear strength of RC deep beams with/without web reinforcements.” Eng. Struct. 235 (May): 111979. https://doi.org/10.1016/j.engstruct.2021.111979.
Feng, D.-C., W.-J. Wang, S. Mangalathu, and E. Taciroglu. 2021d. “Interpretable XGBoost- SHAP machine-learning model for shear strength prediction of squat RC walls.” J. Struct. Eng. 147 (11): 04021173. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003115.
Feng, D.-C., and G. Wu. 2022. “Interpretable machine learning-based modeling approach for fundamental properties of concrete structures.” [In Chinese.] J. Build. Struct. 43 (4): 228. https://doi.org/10.14006/j.jzjgxb.2020.0491.
Friedman, J. H. 2017. The elements of statistical learning: Data mining, inference, and prediction. New York: Springer.
Fu, B., and D.-C. Feng. 2021. “A machine learning-based time-dependent shear strength model for corroded reinforced concrete beams.” J. Build. Eng. 36 (Apr): 102118. https://doi.org/10.1016/j.jobe.2020.102118.
Gino, D., P. Castaldo, L. Giordano, and G. Mancini. 2021. “Model uncertainty in non-linear numerical analyses of slender reinforced concrete members.” Struct. Concr. 22 (2): 845–870. https://doi.org/10.1002/suco.202000600.
Gondia, A., M. Ezzeldin, and W. El-Dakhakhni. 2020. “Mechanics-guided genetic programming expression for shear-strength prediction of squat reinforced concrete walls with boundary elements.” J. Struct. Eng. 146 (11): 04020223. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002734.
Gordon, J. E. 2003. Structures: Or why things don’t fall down. 2nd ed. Boston: Da Capo.
Guan, X., H. Burton, M. Shokrabadi, and Z. Yi. 2021. “Seismic drift demand estimation for steel moment frame buildings: From mechanics-based to data-driven models.” J. Struct. Eng. 147 (6): 04021058. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003004.
Han, T., A. Siddique, K. Khayat, J. Huang, and A. Kumar. 2020. “An ensemble machine learning approach for prediction and optimization of modulus of elasticity of recycled aggregate concrete.” Constr. Build. Mater. 244 (May): 118271. https://doi.org/10.1016/j.conbuildmat.2020.118271.
Kaviani, P., F. Zareian, and E. Taciroglu. 2012. “Seismic behavior of reinforced concrete bridges with skew-angled seat-type abutments.” Eng. Struct. 45 (Dec): 137–150. https://doi.org/10.1016/j.engstruct.2012.06.013.
Ke, G., Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.-Y. Liu. 2017. “Lightgbm: A highly efficient gradient boosting decision tree.” In Vol. 30 of Advances in neural information processing systems, 3146–3154. La Jolla, CA: Neural Information Processing Systems.
Kitayama, S., and M. C. Constantinou. 2018. “Collapse performance of seismically isolated buildings designed by the procedures of ASCE/SEI 7.” Eng. Struct. 164 (Jun): 243–258. https://doi.org/10.1016/j.engstruct.2018.03.008.
Kitayama, S., and M. C. Constantinou. 2019. “Probabilistic seismic performance assessment of seismically isolated buildings designed by the procedures of ASCE/SEI 7 and other enhanced criteria.” Eng. Struct. 179 (Jan): 566–582. https://doi.org/10.1016/j.engstruct.2018.11.014.
Koc, E., B. Cetiner, A. Rose, L. Soibelman, E. Taciroglu, and D. Wei. 2020. “CRAFT: Comprehensive resilience assessment framework for transportation systems in urban areas.” Adv. Eng. Inf. 46 (Oct): 101159. https://doi.org/10.1016/j.aei.2020.101159.
Kolozvari, K., et al. 2019. “State-of-the-art in nonlinear finite element modeling of isolated planar reinforced concrete walls.” Eng. Struct. 194 (Sep): 46–65. https://doi.org/10.1016/j.engstruct.2019.04.097.
Li, Y., Y. Wang, and B. Wu. 2020. “Short-term direct probability prediction model of wind power based on improved natural gradient boosting.” Energies 13 (18): 4629. https://doi.org/10.3390/en13184629.
Lotfollahi, M., M. M. Alinia, and E. Taciroglu. 2015. “Criteria for balanced design of diagonally braced moment resisting frames based on hierarchical yielding and failure sequences and their application.” Eng. Struct. 87 (Mar): 198–219. https://doi.org/10.1016/j.engstruct.2014.12.010.
Lu, X., Y. Xu, Y. Tian, B. Cetiner, and E. Taciroglu. 2021. “A deep learning approach to rapid regional post-event seismic damage assessment using time-frequency distributions of ground motions.” Earthquake Eng. Struct. Dyn. 50 (6): 1612–1627. https://doi.org/10.1002/eqe.3415.
Lyu, Y.-F., G.-Q. Li, and Y.-B. Wang. 2020. “Behavior-based resistance model for bearing-type connection in high-strength steels.” J. Struct. Eng. 146 (7): 04020109. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002639.
Mander, J. B., M. J. Priestley, and R. Park. 1988. “Theoretical stress-strain model for confined concrete.” J. Struct. Eng. 114 (8): 1804–1826. https://doi.org/10.1061/(ASCE)0733-9445(1988)114:8(1804).
Mangalathu, S. 2017. “Performance based grouping and fragility analysis of box-girder bridges in California.” Ph.D. thesis, School of Civil and Environmental Engineering, Georgia Institute of Technology.
Mangalathu, S., S.-H. Hwang, and J.-S. Jeon. 2020. “Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach.” Eng. Struct. 219 (Sep): 110927. https://doi.org/10.1016/j.engstruct.2020.110927.
Mangalathu, S., and J.-S. Jeon. 2019. “Machine learning–based failure mode recognition of circular reinforced concrete bridge columns: Comparative study.” J. Struct. Eng. 145 (10): 04019104. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002402.
Mangalathu, S., and J.-S. Jeon. 2020. “Regional seismic risk assessment of infrastructure systems through machine learning: Active learning approach.” J. Struct. Eng. 146 (12): 04020269. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002831.
Massone, L. M., and F. Melo. 2018. “General solution for shear strength estimate of RC elements based on panel response.” Eng. Struct. 172 (Oct): 239–252. https://doi.org/10.1016/j.engstruct.2018.06.038.
Matheson, J. E., and R. L. Winkler. 1976. “Scoring rules for continuous probability distributions.” Manage. Sci. 22 (10): 1051–1173. https://doi.org/10.1287/mnsc.22.10.1087.
Ning, C.-L., and B. Li. 2017. “Probabilistic development of shear strength model for reinforced concrete squat walls.” Earthquake Eng. Struct. Dyn. 46 (6): 877–897. https://doi.org/10.1002/eqe.2834.
Park, J. W., and D. Kuchma. 2007. “Strut-and-tie model analysis for strength prediction of deep beams.” ACI Struct. J. 104 (6): 657–666.
Peng, T., X. Zhi, Y. Ji, L. Ji, and Y. Tian. 2020. “Prediction skill of extended range 2-m maximum air temperature probabilistic forecasts using machine learning post-processing methods.” Atmosphere 11 (8): 823. https://doi.org/10.3390/atmos11080823.
Rao, C., H. Sun, and Y. Liu. 2021. “Physics-informed deep learning for computational elastodynamics without labeled data.” J. Eng. Mech. 147 (8): 04021043. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001947.
Skiadopoulos, A., A. Elkady, and D. G. Lignos. 2021. “Proposed panel zone model for seismic design of steel moment-resisting frames.” J. Struct. Eng. 147 (4): 04021006. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002935.
Taffese, W. Z., and E. Sistonen. 2017. “Machine learning for durability and service-life assessment of reinforced concrete structures: Recent advances and future directions.” Autom. Constr. 77 (May): 1–14. https://doi.org/10.1016/j.autcon.2017.01.016.
Xie, Y., M. E. Sichani, J. E. Padgett, and R. DesRoches. 2020. “The promise of implementing machine learning in earthquake engineering: A state-of-the-art review.” Earthquake Spectra 36 (4): 1769–1801. https://doi.org/10.1177/8755293020919419.
Xie, Y., Q. Zheng, C.-S. W. Yang, W. Zhang, R. DesRoches, J. E. Padgett, and E. Taciroglu. 2019. “Probabilistic models of abutment backfills for regional seismic assessment of highway bridges in California.” Eng. Struct. 180 (Feb): 452–467. https://doi.org/10.1016/j.engstruct.2018.11.058.
Xu, J.-G., Z.-K. Cai, and D.-C. Feng. 2021a. “Life-cycle seismic performance assessment of aging RC bridges considering multi-failure modes of bridge columns.” Eng. Struct. 244 (Oct): 112818. https://doi.org/10.1016/j.engstruct.2021.112818.
Xu, J.-G., G. Wu, D.-C. Feng, and J.-J. Fan. 2021b. “Probabilistic multi-hazard fragility analysis of RC bridges under earthquake-tsunami sequential events.” Eng. Struct. 238 (Jul): 112250. https://doi.org/10.1016/j.engstruct.2021.112250.
Xu, Y., X. Lu, B. Cetiner, and E. Taciroglu. 2021c. “Real-time regional seismic damage assessment framework based on long short-term memory neural network.” Comput.-Aided Civ. Infrastruct. Eng. 36 (4): 504–521. https://doi.org/10.1111/mice.12628.
Zhang, C., and Y. Ma. 2012. Ensemble machine learning: Methods and applications. New York: Springer.
Zhang, J., C. Wan, and T. Sato. 2013. “Advanced Markov chain Monte Carlo approach for finite element calibration under uncertainty.” Comput.-Aided Civ. Infrastruct. Eng. 28 (7): 522–530. https://doi.org/10.1111/j.1467-8667.2012.00802.x.
Information & Authors
Information
Published In
Journal of Structural Engineering
Volume 148 • Issue 8 • August 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Nov 17, 2021
Accepted: Mar 17, 2022
Published online: May 27, 2022
Published in print: Aug 1, 2022
Discussion open until: Oct 27, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Zhen Sun, Xiao-Wei Ye, Jun Lu, Estimating stay cable vibration under typhoon with an explainable ensemble learning model, Structure and Infrastructure Engineering, 10.1080/15732479.2023.2165121, (1-13), (2023).
- De-Cheng Feng, Yue Li, Abdollah Shafieezadeh, Ertugrul Taciroglu, Advances in Data-Driven Risk-Based Performance Assessment of Structures and Infrastructure Systems, Journal of Structural Engineering, 10.1061/JSENDH.STENG-12434, 149, 5, (2023).
- Shi-Zhi Chen, Shu-Ying Zhang, De-Cheng Feng, Ertugrul Taciroglu, Embedding Prior Knowledge into Data-Driven Structural Performance Prediction to Extrapolate from Training Domains, Journal of Engineering Mechanics, 10.1061/JENMDT.EMENG-7062, 149, 12, (2023).
- Haoyou Zhang, Xiaowei Cheng, Yi Li, Dianjin He, Xiuli Du, Rapid seismic damage state assessment of RC frames using machine learning methods, Journal of Building Engineering, 10.1016/j.jobe.2022.105797, 65, (105797), (2023).
- Zhen Sun, Dionysius M. Siringoringo, Shi-zhi Chen, Jun Lu, Cumulative displacement-based detection of damper malfunction in bridges using data-driven isolation forest algorithm, Engineering Failure Analysis, 10.1016/j.engfailanal.2022.106849, 143, (106849), (2023).
- Yong Mei, Yunhou Sun, Feng Li, Xiangyun Xu, Ao Zhang, Jun Shen, Probabilistic prediction model of steel to concrete bond failure under high temperature by machine learning, Engineering Failure Analysis, 10.1016/j.engfailanal.2022.106786, 142, (106786), (2022).